Eran Steinberg

In-camera person-indexing of digital images

A prototype implementation of an automatic in-camera cataloging tool is presented. An external infrastructure to store and analyze images and support the in-camera cataloging tool is also described.

Automated in-camera detection of flash-eye defects

This paper examines the problem of performing automated real-time detection of flash eye dejects (redeye) in the firmware of a digital camera. Several different algorithms are compared, timing and memory requirements on several embedded architectures are presented. A discussion on advanced in-camera techniques to improve on standard algorithms is also presented.

Internet enabled digital photography

The exposure of consumers to the Internet is opening up broad new markets for data-centric services and products. One of these new markets is that of digital photography. A key to growing this emerging market segment lies in simplifying the mechanisms for connecting digital cameras and other sources of digital images to the Internet. We describe a number of mechanisms of achieving such connectivity using existing desktop PC and Web technology, and additionally using a new generation of consumer Internet appliances. In addition details are given of the server-side infrastructure required to support a range of network-oriented services.

Wireless transfer of images from a digital camera to the Internet via a standard GSM mobile phone

In this paper we describe an infrastructure based on an existing, commercially available, GSM mobile phone for achieving connectivity between digital cameras and an Internet Website. Pictures are loaded from a standard digital camera, or compact flash card, by an embedded appliance, which establishes the Internet connection and controls the transfer of pictures from the camera to a remote website. Detailed descriptions are given of this picture transfer appliance and of a typical website infrastructure to store and manage the pictures and provide end-user services.

PTP/IP - a new transport specification for wireless photography

PTP (picture transfer protocol ISO-15740) is an international standard for connectivity and interface of digital photography devices. In this paper, we describe how PTP can be extended to work over generic TCP/IP networks. As digital cameras and printers becomes wireless, PTP/IP provides the necessary flexibility of applications infrastructure for networked digital photography.

Internet connectivity solutions for digital photography

The exposure of consumers to the Internet is opening up broad new markets for data-centric services and products. One of these new markets is that of digital photography. A key to growing this emerging market segment lies in simplifying the mechanisms for connecting digital cameras and other sources of digital images to the Internet. In this paper we describe a number of mechanisms of achieving such connectivity using existing desktop PC and Web technology, and additionally using a new generation of consumer Internet appliances. In addition, details are given of the server-side infrastructure required to support a range of network-oriented services.

PTP/IP Adapter Design and Connectivity Techniques for Legacy Imaging Appliances

PTP/IP is an emerging connectivity standard for networked imaging appliances. It combines the ease of use and seamless connectivity of Picture Transfer Protocol (PTP) with the ubiquity of TCP/IP networks. In this paper we examine methods to enable legacy PTP appliances to gain the benefits of PTP/IP through the design of bridge and gateway adapters which can be simply plugged into the USB ports of such appliances. The internal firmware stacks of such adapters are described and practical case studies describe the adaptation of legacy PTP cameras and printers to connect over a conventional 802.11 wireless LAN.

Enabling Legacy PTP Cameras and Printers as Networked PTP/IP Appliances

PTP/IP is a new connectivity standard for networked imaging appliances which combines the ease of use and seamless connectivity of picture transfer protocol (PTP) with the ubiquity of TCP/IP networks. In this paper we examine methods to allow legacy PTP appliances to gain the benefits of PTP/IP through the design of bridge and gateway adapters which can be simply plugged into the USB ports of such appliances. The internal firmware stacks of such adapters are described and practical case studies describe the adaption of legacy PTP cameras and printers to connect over a conventional 802.11 wireless LAN.

People first: separating people from background in digital photographs

Extracting people from background in digital photography is a task of great importance, with many applications for digital cameras. Yet, the task poses a number of challenging technical problems to be tackled. In this paper we propose a novel technique for people extraction from background which is both accurate and of low computational complexity therefore amenable to be embedded in digital cameras. The proposed technique uses frames from the camera live view mode (called previews) (now widely available in digital cameras and even in the latest DSLRs) in conjunction with the flash. The basic principle of the method is to acquire two images of the same scene, one with flash and the other without. The use of preview images over two captured images makes the solution easily embeddable in digital cameras. In the proposed setup, in daylight conditions, the flash is triggered at the time of the penultimate preview image. The mask of the subject is then computed based on the intensity difference between the last two previews. For night scenes, where the flash power is required for the acquisition of the actual picture, the subject is detected based on the intensity difference between the final image downsampled to the size of the preview and the average of the last two previews. Additional problems posed by this setup, e.g. misalignments, false positives, incomplete subject map, are also addressed. The resulting foreground map is further used to obtain a narrow depth-of-field version of the initial photograph, by keeping the foreground unaltered while blurring the background.

Picture Management using Person Retrieval for Consumer Image Collections

In the last years the huge evolution of digital photography lead to an increasing interest in developing algorithms for indexing and classifying collections of digital images. This paper presents an automatic system for organizing and browsing through consumer digital image collections using the persons in the images as patterns. In order to implement such an automatic system we have to detect and classify the people in the images according to their similarities. For this we employ algorithms for face detection, face recognition and additional methods to cope with large variations that are usually present in consumer images. These additional methods includes using more than one type of classifiers for face recognition and also using additional information about the person characteristics extracted from other region than the face. This additional information will be more robust to factors that influence the accuracy of classical face recognition systems when working with consumer images. The proposed system was tested using a typical consumer image collection and practical applications using the system are presented in the end.